© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59294
    Prev
    Next
    INDEX
    Explanations

    HTML element structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     感じ
    -1.73
     the
    -1.61
     is
    -1.53
    васто
    -1.52
    bohemian
    -1.52
    islamic
    -1.51
     suele
    -1.51
     その
    -1.49
    ICIOS
    -1.49
     was
    -1.46
    POSITIVE LOGITS
    <bos>
    1.80
    a
    1.67
    őtt
    1.66
    儿的
    1.58
    y
    1.57
     only
    1.50
    了一会儿
    1.49
     DevComponents
    1.47
     Нам
    1.43
    er
    1.41
    Activations Density 0.017%

    No Known Activations